基于PCL三维点云花瓣分割与重建  

Petal segmentation and reconstruction based on PCL 3D point cloud

作　　者：任彪 陆玲[1] REN Biao;LU Ling(Institute of Information Engineering,East China University of Technology,Nanchang 330013,China)

机构地区：[1]东华理工大学信息工程学院,江西南昌330013

出　　处：《现代电子技术》2022年第12期149-154,共6页Modern Electronics Technique

基　　金：国家自然科学基金资助项目(61761003)。

摘　　要：三维点云数据的单木植物器官分割的研究仍处于起步阶段,对于植物器官的精确分割还未形成有效的解决方法,对于单个花朵点云分割出花瓣的研究更是少见。为此,文中提出一种基于PCL库三维点云花瓣分割的研究方法,以单个百合花朵三维点云数据为研究对象,对其进行花瓣分割。该方法主要是以PCL库为开发工具,首先对三维点云数据进行体素化下采样处理;其次结合K-means聚类分割算法计算点云曲率值,并根据点云曲率值以及点云形态特征确定K值;再利用鼠标交互方法确定初始聚类中心,从而达到花瓣分割的目的;最后使用贪婪投影三角网格化算法来实现花瓣的重建。实验结果表明,文中方法能够对花瓣进行有效分割,且用时少、准确率高,利用三角化重建能更好地保存花朵的形态特征,稳定性好。The research on single tree plant organ segmentation of 3D(three-dimensional)point cloud data is still in its infancy,and there is no effective solution for the accurate segmentation of plant organs,especially for the petals segmentation from a single flower point cloud. Therefore,a research method of petal segmentation based on 3D point cloud of PCL(point cloud library) is proposed,and the petal segmentation is carried out by taking 3D point cloud data of a single lily as the research object. In this method,the PCL is taken as the development tool,voxelized down-sampling processing is carried out on3D point cloud data,the curvature value of the point cloud is calculated by means of the K-means clustering segmentation algorithm,and then the K value is determined according to the curvature value of the point cloud and the morphological characteristics of point cloud. The mouse interaction method is used to determine the initial clustering center,so as to achieve the purpose of petal segmentation. The greedy projection triangle mesh algorithm is used to reconstruct the petals. The experimental results show that this method can segment petals effectively,and has high time efficiency and accuracy. The triangularization reconstruction can better preserve the morphological characteristics of flowers and has good stability.

关 键 词：三维点云分割 花瓣分割 PCL 三角化重建 曲率特征 体素化处理 

分 类 号：TN911.73-34[电子电信—通信与信息系统] TP391.41[电子电信—信息与通信工程]